Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis

TL;DR

This comprehensive review analyzes how transformers and language models have advanced form understanding in scanned documents, highlighting recent trends, datasets, and the evolution of techniques over the past decade.

Contribution

It offers an in-depth survey of recent developments, emphasizing the impact of transformers and language models on form understanding in noisy scanned documents.

Findings

Transformers have significantly improved form understanding accuracy.

New datasets provide benchmarks for evaluating model performance.

Language models effectively handle noisy and complex scanned documents.

Abstract

This paper presents a comprehensive survey of research works on the topic of form understanding in the context of scanned documents. We delve into recent advancements and breakthroughs in the field, highlighting the significance of language models and transformers in solving this challenging task. Our research methodology involves an in-depth analysis of popular documents and forms of understanding of trends over the last decade, enabling us to offer valuable insights into the evolution of this domain. Focusing on cutting-edge models, we showcase how transformers have propelled the field forward, revolutionizing form-understanding techniques. Our exploration includes an extensive examination of state-of-the-art language models designed to effectively tackle the complexities of noisy scanned documents. Furthermore, we present an overview of the latest and most relevant datasets, which serve as essential benchmarks for evaluating the performance of selected models. By comparing and contrasting the capabilities of these models, we aim to provide researchers and practitioners with useful guidance in choosing the most suitable solutions for their specific form understanding tasks.